Tool Chatter Research Articles

Online real-time machining chatter sound detection using convolutional neural network by adopting expert knowledge

In machining processes, chatter detection remains a pivotal challenge, impacting both the quality and efficiency of manufacturing operations. This study introduces an approach that synergizes expert knowledge with the capabilities of advanced convolutional neural networks (CNNs) to enhance chatter detection. A comprehensive monitoring framework is proposed to adopt expert knowledge that digitizes machine tool and sound data, effectively labeling chatter events. This study merges human expertise in identifying milling tool chatter sounds with CNN architecture, marking a notable advancement in blending machining insights of experts with modern artificial intelligence (AI) technologies. The proposed chatter prediction architecture is distinguished by its incorporation of an attention block, fusing outputs from the AlexNet model with cutting parameters. This model outshines baseline models in both in-distribution (ID) and out-of-distribution (OOD) testing datasets. In OOD testing, the proposed model achieved an impressive accuracy of 94.51%, markedly surpassing the standalone CNN model’s accuracy of 88.66%. Real-time 3D visualization of machining operations is demonstrated through the successful implementation of the trained model on a Raspberry Pi.

Classification Model for Real-Time Monitoring of Machining Status of Turned Workpieces

The occurrence of tool chatter can have a detrimental impact on the quality of the workpiece. In order to improve surface quality, machining stability, and reduce tool wear cycles, it is essential to monitor the workpiece machining process in real time during the turning process. This paper presents a tool chatter state recognition model based on a denoising autoencoder (DAE) for feature dimensionality reduction and a bidirectional long short-term memory (BiLSTM) network. This study examines the feature dimensionality reduction method of the DAE, whereby the reduced-dimensional data are concatenated and input into the BiLSTM model for training. This approach reduces the learning difficulty of the network and enhances its anti-interference capability. Turning experiments were conducted on a SK50P lathe to collect the dataset for model performance validation. The experimental results and analysis indicate that the proposed DAE-BiLSTM model outperforms other models in terms of prediction and classification accuracy in distinguishing between stable machining, over-machining, and severe chatter stages in turning chatter state recognition. The overall classification accuracy reached 96.28%.

Chatter and Surface Waviness Analysis in Oerlikon Face Hobbing of Spiral Bevel Gears

A vectorized analytical model for the cutting dynamics in the spiral bevel gear face hobbing process has been developed, which is based on machine tool kinematics and vibration vectorization. The structural modal parameters of the cutter head spindle system are obtained through experimental modal analysis with hammer impact testing. The analytical model is utilized to simulate the generation of simulated vibration acceleration signals during spiral bevel gear hobbing. A wavelet threshold denoising method is applied to process the simulated vibration signals of the spiral bevel gear face hobbing with added white noise. Signal processing methods, including short-time Fourier transform are employed for time-domain analysis, frequency-domain analysis, and time–frequency-domain analysis of measured signals and simulated signals, thereby extracting the corresponding statistical features. In addition to the results of the experimental modal analysis, the causes of chatter in spiral bevel gear hobbing are discussed in detail, revealing that the main factor is cutter head vibration in the Y direction of the Hunan ZDCY CNC EQUIPMENT YKA2260 machine tool used in this research. The error in the time-domain characteristic parameters between simulated signals and measured vibration acceleration signals is within 15%, with a difference of 3.5% in spectral peak values. The predicted tooth surface morphology from simulation matches the actual morphology on the workpiece, comprehensively validating the reliability of the cutting dynamics model for the spiral bevel gear face hobbing process. Another conclusion drawn from numerical simulation experiments is that the amount of tooth surface waviness of the spiral bevel gears is the ratio of tool chatter frequency to cutting fundamental frequency.

Tool Chatter Diagnosis using EMD and LMD Techniques: A Comparative Study

Tool Chatter Diagnosis using EMD and LMD Techniques: A Comparative Study

Chatter Identification of Vibration Signals and Surface Roughness using Wavelet Transform and I-kazTM Methods

The paper describes the method to identify chatter in low-cutting-speed operations. It is based on vibration and surface roughness measurements. Tool chatter is the self-excited relative motion between the cutting tool and work piece. Tool chatter leads to poor surface quality and tool wear. The LMS Scadas testing system and accelerometer were used to measure the vibration signals during the turning operation, and Marsuft Psi was used to measure the surface roughness. When various cutting parameter combinations, such as cutting speed, feed rate, and depth of cut, were employed throughout the machining process, chatter and vibrating phenomena occurred. After the recorded signals were analyzed using the wavelet transform (WT), a chatter index (CI) was produced to determine how severe the chatter was. According to the results analysis, the experimental study demonstrated the close relationship between the surface roughness values and the chatter index when evaluating chatter identification.

Optimization of electrolyte flow field for electrochemical boring of inner cavity in 07Cr16Ni6 high-strength steel

Inner cavity structures are a type of functional feature that can reduce the weight and increase the operating speed of spindles. They have been widely used in the aviation, aerospace, and automobile fields. Since these cavities are located deep inside spindles, boring tool bars need to be designed to be sufficiently long, which results in tool chatter. Moreover, this makes the machining accuracy and surface quality difficult to control. Herein, a new method of electrochemical boring is proposed. In this method, the workpiece rotates around its axis, a long-nozzle tool is linearly fed along the diameter direction, and the entire inner cavity is processed in a single tool-feed operation. In this work, a flow-field model for electrochemical boring was established, and the axial flow-field distribution of the nozzle was simulated. To improve the uniformity of the electrolyte flow field, a nozzle structure with a variable cross section is proposed. An optimized nozzle structure was obtained via the golden-section method. Finally, comparative electrochemical boring experiments with constant and variable cross-section tools were conducted for an inner cavity length of 420 mm in 07Cr16Ni6 high-strength steel with 20 wt% NaNO3 solution. The results indicate that the specimen processed by the optimized variable cross-section tool had higher inner-diameter accuracy. The diameter deviation of the final inner cavity was found to be within ± 0.04 mm, the wall-thickness deviation of the specimen was within ± 0.02 mm, and the inner surface roughness was less than Ra = 0.5 µm. These experimental results verify the effectiveness of the flow-field simulations and the optimization of the cathode structure.

Chatter-suppressing ruling method based on double-layer elastic support.

A cross-hinge spring is the preferred support for a ruling tool because of its excellent flexibility. However, there are high precision requirements for the tool installation, which make the installation and adjustments difficult. There also is poor robustness against interference, which readily results in tool chatter. These issues affect the quality of the grating. This paper proposes an elastic ruling tool carrier with a double-layer parallel-spring mechanism, establishes a torque model of the spring, and analyzes its force state. In a simulation, the spring deformation and frequency modes of the two ruling tool carriers are compared and the overhang length of the parallel-spring mechanism is optimized. In addition, the performance of the optimized ruling tool carrier is analyzed in a grating ruling experiment to verify the carrier's effectiveness. The results show that compared to the cross-hinge elastic support, the deformation of the parallel-spring mechanism by a ruling force in the X direction is on the same order of magnitude. However, the deformation in the Y direction is reduced by a factor of 270, and the deformation in the Zdirection is reduced by a factor of 32. The torque of the proposed tool carrier is slightly higher (12.8%) in the Z direction but lower by a factor of 2.5 in the X direction and by a factor of 60 in the Y direction. The overall stiffness of the proposed tool carrier is improved and the first-order frequency of the proposed structure is higher by a factor of 2.8. The proposed tool carrier thus better suppresses chatter, effectively reducing the effect of the ruling tool installation error on the grating quality. The flutter suppression ruling method can provide a technical basis for further research on high-precision grating ruling manufacturing technology.

Numerical Evaluations for Robotic Turning with a Scheduled Modulatory Gain-Based Chatter Controller

During the turning production process, a material is cut by using a specified material removal strategy in order to produce the desired final form and dimension. Tool chatter is a widespread undesired dynamic instability that arises during fundamental machining processes such as milling, drilling, and turning. The dynamic interaction of the components of the cutter tool and the surface of the material being cut is just one of the numerous process variables that can result in chatter vibrations. Usually, the vigorous turning that quickly releases the metal chip causes the cutter to oscillate excessively with respect to the workpiece. Tool chatter can result in excessive wear, a shorter tool life, poor surface quality, and misaligned geometry. Due to the poor quality of the surface finish, this can consequently result in greater prices, postponed deliveries, and even lost orders. The ability of a gain modulation-based control strategy to improve the product finish in robotic turning has been examined in this investigation along with a number of other process parameters. A two-link manipulator dynamical model has been used and numerical outcomes are presented for the efficacy of the control toward achieving an improved product surface finish.

Finite Element Analysis and Experimental Investigation of Tool Chatter in Ultra-Precision Diamond Micro-Milling Process

Ultra-precision milling with an aerostatic high-speed spindle and a single-crystal diamond micro-tool is promising for the fabrication of miniaturized complex parts. While tool chatter occurring in milling processes has a substantial effect on the machined surface formation, a fundamental understanding of the tool chatter behavior in ultra-precision milling is essentially required for achieving an ultra-high surface finish. In this paper, through a combination of finite element simulations and experimental validations, the machining mechanisms of the ultra-precision diamond micro-milling of a copper workpiece are revealed, in which the tool chatter behavior and its correlation with the machined surface morphology are emphatically studied. Specifically, the correlation between the tool chatter and the transient depth of cut is analytical established. Subsequently, we first establish a finite element model of diamond micro-milling with the consideration of milling tool deformation and material removal to reveal the tool chatter behavior during the milling process. Furthermore, a corresponding micro-milling experiment is also conducted to validate the simulation results in terms of the milling force, chip profile and morphology of machined surfaces. Finally, the effect of spindle speed on the milling process in particular tool chatter is investigated by FE simulations, through which a linear relationship between the spindle speed and microscopic roughness Rz of a machined surface is obtained. The research findings provide a theoretical basis for understanding the origination of tool chatter in the diamond micro-milling process, as well as the rational selection of machining parameters for suppressing the tool chatter.

Signal Processing Algorithms Like Ensemble Empirical Mode Decomposition and Statistical Analysis-Based Tool Chatter Severity Prediction

The identification of faults in machinery is a very emerging trend. In the last few decades, regenerative tool chatter and its adverse effects have been explored by many researchers. However, a lot of work has to be done within this domain. A new methodology has been presented in the present work to determine the chatter severity while machining. The methodology has three stages. In the first stage, numerous experiments have been carried out, and associated signals have been captured. Thereafter, in the second stage, preprocessing of the recorded signals have been done using “ensemble empirical mode decomposition” to filter out the contaminations from the signals. The intrinsic mode functions have been further evaluated using statistical indicators viz. chatter index and absolute mean amplitude. In the third stage, these statistical indicators have been examined concerning the input parameters to identify the variation in the responses and chatter severity. The proposed methodology seems helpful for the researchers to identify the chatter features concerning variation in input parameters.

Measurement of Tool Chatter and MRR Using Sound Signal During Milling of Al 6061-T6

Measurement of Tool Chatter and MRR Using Sound Signal During Milling of Al 6061-T6

Dynamic stability of a paralle kinematic machine

Machine tool chatter causes machining instability, surface roughness, and tool wear in metal cutting processes. A stability lobe diagram based on the theory of regenerative vibration is an effective tool to predict and control the chatter. This paper presents the advances in the mechanical design of a parallel kinematic machine tool. The features that make it ideal for machining tasks, and that make unique in its own way, are highlighted. In addition, the description of the progress of this work will be focused on the analysis of the stability limitation for machining systems to derive the stability lobe diagram with modal analysis of the spindle. A vibratory model is developed by adding cutting forces and including analytical equations for the depth of cut and for the cutting speeds, both depending on the frequency of vibration. A step-by-step procedure provides a stability lobe diagram. The results show that it is relatively easy to provide a relationship between depth of cut and spindle speed. In turn, it makes it easy to compare machining processes under different cutting parameters and conditions.

Analysis of Regenerative Raw Signals Using Variational Mode Decomposition

Faults like regenerative tool chatter have been evaluated by several researchers in order to suppress its adverse effect. However, many facets of this domain are yet to be addressed. In the present work, a new methodology has been proposed to process the recorded regenerative chatter signals in order to extract the chatter features. In the proposed approach, experiments have been performed and signals pertaining to regenerative tool chatter have been recorded using microphone. Thereafter, the recorded signals have been evaluated and preprocessed using variational mode decomposition (VMD) in order to extract chatter features. The decomposed signals that result in variational mode functions have been further evaluated by calculating a response termed as chatter index. This response has been used to predict the chatter severity during machining at different combinations of input parameters, on verifying the obtained results it has been found that the proposed methodology is significant in identifying the chatter severity.

A novel ensemble method based on the SBLMD-ANN-MOPSO approach for predicting milling stability regimes

In recent decades, a lot of work has been done to mitigate self-excited vibration effects in milling operations. Still, a robust methodology is yet to be developed that can suggest stability bounds pertaining to higher metal removal rates (MRRs). In the present work, experimentally-acquired acoustic signals in milling operations have been computed using a modified spline-based local mean decomposition technique in order to cite tool chatter features. Further, three artificial neural network training algorithms; resilient propagation, conjugate gradient-based and Levenberg–Marquardt algorithms, and two activation functions; hyperbolic tangent sigmoid and log sigmoid, have been used to train the acquired chatter vibration and MRR data set. Over-fitting or under-fitting issues may arise from the random selection of a number of hidden neurons. The solution to these problems is also proposed in this paper. Among these training algorithms and activation functions, a suitable one has been selected and further invoked to develop prediction models of chatter severity and MRR. Finally, multi-objective particle swarm optimization has been invoked to optimize the developed prediction models to obtain the most favourable range of input parameters pertaining to stable milling with higher productivity.

Tool Chatter State Identification Method Based on Dae-Bilstm Model

Tool Chatter State Identification Method Based on Dae-Bilstm Model

Milling Processes With Active Damping: Modeling and Stability

Abstract Active dampers are on the verge of appearing in commercial machines as devices that assist the avoidance of machine tool chatter. The adjustment of control parameters in these devices is mostly guided by models that do not consider the dynamics within the control loop of active damper. Therefore, these models neglect the dynamics of actuation, measurement, and filtering, which can result in inaccurate stability predictions that hinder the efficient tuning of active dampers. To formulate a more realistic model for milling processes assisted by active damping, this paper derives a novel mathematical model that takes into account the internal dynamics of the actuator, measuring device, and discrete filtering. This study shows that accurate stability prediction requires the incorporation of actuator and filter dynamics into the model, especially at high spindle speeds and large feedback gains.

Chatter in milling with robots with structural nonlinearity

Stiffness and damping nonlinearities are often negligible in machine tool vibrations, but they are shown to be prominent in industrial robots that are used for milling, mainly due to the several nonlinear phenomenon that occur in the robot’s revolute joints. In this paper, a 2DOF nonlinear vibratory model is presented to study regenerative chatter in robotic milling. The presented model includes cubic stiffness and damping terms to account for the robot’s structural nonlinearities. The machining forces are represented by a combination of periodic forces and delayed vibration terms; the former is generated by the feed motion of the tool and the later by chip regeneration. Furthermore, the machining force model is non-smooth due to (a) periodic entrance and exit of the cutting edges to and from the cutting region, and (b) loss-of-contact at high-amplitude oscillations. The dynamics in the presented model is therefore described by a set of nonlinear Delay Differential Equations with periodic coefficients and non-smooth forces. Numerical continuation with smoothing techniques is used to determine the combinations of spindle speed and axial depth of cut at which the forced periodic vibrations go through secondary Hopf or period doubling bifurcations, causing chatter in the milling process. A KUKA robotic arm with milling end-effector is used as a case study. The presented analysis shows that feedrate, which has no effect on chatter in machine tools with linear dynamics, alters the stability of vibrations in milling systems with nonlinear structural dynamics. Nonlinear systems’ stiffness and damping depend on vibration amplitude. Since feedrate directly influences the amplitude of forced vibrations, the nonlinear system’s damping and stiffness and consequently its chatter stability changes by feedrate.

Comparative study of EMD and SBLMD signal processing techniques to assess vibration in machining

In this work, acquired machining sound signals are analyzed using two signal processing techniques, i.e., Empirical Mode decomposition (EMD) and the new Local Mean Decomposition (SBLMD) technique. Among this the most suitable one for regenerative chatter identification is selected. Thereafter, correlation coefficient (CC) and relative energy rule (RER) has been invoked to detect the major PF’s. Further, tool chatter features are explored by using a novel Chatter Indicator (CI). Finally, confirmation test have been performed in order to validate the proposed methodology and outcomes show that proposed chatter indicator can be effectively used to detect tool chatter.

SB-LMD based online monitoring of tool chatter detection in milling process

In this present study, an experimental approach for detecting tool chatter in its early stages is proposed. Local mean decomposition based on cubic spline approach is invoked to analyse acquired machining sound data at varied cutting settings. The correlation coefficient and relative energy rule are used to identify the significant PFs. Furthermore, the characteristics of tool chatter are investigated by assessing six dimensional and six dimensionless indexes. Then, for every combination of characteristics, a threshold is defined to detect the aforementioned severity of chatter. At last, tool chatter online monitoring is carried out based on the obtained threshold.

Bi-stability induced by motion limiting constraints on boring bar tuned mass dampers

This paper investigates the effect of displacement constraints on the attenuation performance of tuned mass dampers (TMDs) used in boring and turning applications. A simplified piecewise-smooth mechanical model is investigated through time domain simulations and hybrid periodic orbit continuation, first under harmonic excitation, then under regenerative cutting load. A quasi-frequency response function is derived for impacting TMDs through composition of different families of period-1 orbits, then an acceptability map for turning is formulated based on the appearance of cutting-edge contact-loss and fly-over events. The bi-stable domain boundaries are determined through two parameter continuation of contact-loss grazing events. It is shown that in both cases arising rigid body collisions can significantly hinder TMD damping performance and lead to resonance problems or machine tool chatter.